Automated Cervical Digitized Histology Whole-Slide Image Analysis Toolbox.

BACKGROUND: Cervical intraepithelial neoplasia (CIN) is regarded as a potential precancerous state of the uterine cervix. Timely and appropriate early treatment of CIN can help reduce cervical cancer mortality. Accurate estimation of CIN grade correlated with human papillomavirus type, which is the primary cause of the disease, helps determine the patient's risk for developing the disease. Colposcopy is used to select women for biopsy. Expert pathologists examine the biopsied cervical epithelial tissue under a microscope. The examination can take a long time and is prone to error and often results in high inter-and intra-observer variability in outcomes. METHODOLOGY: We propose a novel image analysis toolbox that can automate CIN diagnosis using whole slide image (digitized biopsies) of cervical tissue samples. The toolbox is built as a four-step deep learning model that detects the epithelium regions, segments the detected epithelial portions, analyzes local vertical segment regions, and finally classifies each epithelium block with localized attention. We propose an epithelium detection network in this study and make use of our earlier research on epithelium segmentation and CIN classification to complete the design of the end-to-end CIN diagnosis toolbox. RESULTS: The results show that automated epithelium detection and segmentation for CIN classification yields comparable results to manually segmented epithelium CIN classification. CONCLUSION: This highlights the potential as a tool for automated digitized histology slide image analysis to assist expert pathologists.

EpithNet: Deep Regression for Epithelium Segmentation in Cervical Histology Images.

BACKGROUND: Automated pathology techniques for detecting cervical cancer at the premalignant stage have advantages for women in areas with limited medical resources. METHODS: This article presents EpithNet, a deep learning approach for the critical step of automated epithelium segmentation in digitized cervical histology images. EpithNet employs three regression networks of varying dimensions of image input blocks (patches) surrounding a given pixel, with all blocks at a fixed resolution, using varying network depth. RESULTS: The proposed model was evaluated on 311 digitized histology epithelial images and the results indicate that the technique maximizes region-based information to improve pixel-wise probability estimates. EpithNet-mc model, formed by intermediate concatenation of the convolutional layers of the three models, was observed to achieve 94% Jaccard index (intersection over union) which is 26.4% higher than the benchmark model. CONCLUSIONS: EpithNet yields better epithelial segmentation results than state-of-the-art benchmark methods.

DeepCIN: Attention-Based Cervical histology Image Classification with Sequential Feature Modeling for Pathologist-Level Accuracy.

BACKGROUND: Cervical cancer is one of the deadliest cancers affecting women globally. Cervical intraepithelial neoplasia (CIN) assessment using histopathological examination of cervical biopsy slides is subject to interobserver variability. Automated processing of digitized histopathology slides has the potential for more accurate classification for CIN grades from normal to increasing grades of pre-malignancy: CIN1, CIN2, and CIN3. METHODOLOGY: Cervix disease is generally understood to progress from the bottom (basement membrane) to the top of the epithelium. To model this relationship of disease severity to spatial distribution of abnormalities, we propose a network pipeline, DeepCIN, to analyze high-resolution epithelium images (manually extracted from whole-slide images) hierarchically by focusing on localized vertical regions and fusing this local information for determining Normal/CIN classification. The pipeline contains two classifier networks: (1) a cross-sectional, vertical segment-level sequence generator is trained using weak supervision to generate feature sequences from the vertical segments to preserve the bottom-to-top feature relationships in the epithelium image data and (2) an attention-based fusion network image-level classifier predicting the final CIN grade by merging vertical segment sequences. RESULTS: The model produces the CIN classification results and also determines the vertical segment contributions to CIN grade prediction. CONCLUSION: Experiments show that DeepCIN achieves pathologist-level CIN classification accuracy.

Extraneural Metastasis of Primary Glioma Occurring in a Setting of Occupational Ionizing Radiation Exposure.

Malignant gliomas account for 60% of all primary brain tumors in adults. Glioblastoma Multiforme (GBM) is the most common primary glial tumor with a dismal prognosis and a median survival of approximately 14 months. Extra-neural metastases from primary brain tumors are unusual with an incidence rate of less than 2%. This has been attributed to factors such as short survival, lack of true lymphatics in the CNS, and physical barriers provided by the dura, extracellular matrix, and basement membrane. Although most GBMs occur sporadically, there is a known association with therapeutic radiation exposure and with work in nuclear disaster cleanup. To our knowledge, no case of GBM with metastasis occurring in a patient with occupational radiation exposure currently exists in the literature. In this article, we present a case of GBM with lung metastasis occurring in a 51-year-old Caucasian male, whose history is significant for occupational exposure to ionizing radiation, and review the literature on GBM risk factors and potential mechanisms of metastasis.

Interobserver reproducibility of The Paris System for Reporting Urinary Cytology.

BACKGROUND: The Paris System for Reporting Urinary Cytology represents a significant improvement in classification of urinary specimens. The system acknowledges the difficulty in cytologically diagnosing low-grade urothelial carcinomas and has developed categories to deal with this issue. The system uses six categories: unsatisfactory, negative for high-grade urothelial carcinoma (NHGUC), atypical urothelial cells, suspicious for high-grade urothelial carcinoma, high-grade urothelial carcinoma, other malignancies and a seventh subcategory (low-grade urothelial neoplasm). METHODS: Three hundred and fifty-seven urine specimens were independently reviewed by four cytopathologists unaware of the previous diagnoses. Each cytopathologist rendered a diagnosis according to the Paris System categories. Agreement was assessed using absolute agreement and weighted chance-corrected agreement (kappa). Disagreements were classified as low impact and high impact based on the potential impact of a misclassification on clinical management. RESULTS: The average absolute agreement was 65% with an average expected agreement of 44%. The average chance-corrected agreement (kappa) was 0.32. Nine hundred and ninety-nine of 1902 comparisons between rater pairs were in agreement, but 12% of comparisons differed by two or more categories for the category NHGUC. Approximately 15% of the disagreements were classified as high clinical impact. CONCLUSIONS: Our findings indicated that the scheme recommended by the Paris System shows adequate precision for the category NHGUC, but the other categories demonstrated unacceptable interobserver variability. This low level of diagnostic precision may negatively impact the applicability of the Paris System for widespread clinical application.

Impact of Consensus Conference Review on Diagnostic Disagreements in the Evaluation of Cervical Biopsy Specimens.

OBJECTIVES: To determine the impact of consensus conferences on the frequency of discrepant cases in a surgical pathology practice. METHODS: The percentage of discrepancies in cases reviewed at a weekly consensus conference was calculated for the first and last months of a 13-month period. Both interrater agreement and agreement with the consensus diagnoses were assessed. A total of 309 diagnoses were performed for the first month and 518 for the last month. Both absolute and chance-corrected agreement were calculated for each period. RESULTS: Absolute agreement rate increased from 91.2% in the first month to 98.2% in the final month. Chance-corrected agreement increased from 0.80 in the first month to 0.97 in the final month. CONCLUSIONS: The consensus conference technique appears to be a useful method to reduce intradepartmental diagnostic discrepancies. Both absolute and chance-corrected agreement are improved by using consensus conferences.

Accuracy and Reproducibility of Nuclear/Cytoplasmic Ratio Assessments in Urinary Cytology Specimens.

BACKGROUND: Evaluation of the nuclear to cytoplasmic ratio is commonly used for assessment of the presence of malignancy and for grading and typing of malignant neoplasms. Despite its widespread usage, little information exists regarding the accuracy and reproducibility of non-automated assessment. METHODS: Forty-seven cells obtained from Papanicolaou stained urine cytologies were assessed by quantitative image analysis for nuclear area and cell area. The nuclear/cytoplasmic ratio was calculated. Visual estimates of the N/C ratio were made by six pathologists. Statistical analysis was performed to determine accuracy, precision, and interrater reliability. RESULTS: True N/C ratios varied from 0.02 to 0.81. 27% of cases demonstrated a true N/C ratio between 0.5 and 0.7. Quantitative estimates of N/C ratios were less precise and less accurate at high N/C ratios. The coefficient of variation was 27%. The majority of raters demonstrated decreased accuracy and precision of estimates as N/C ratio increased. Overall classification accuracy was 73%. Accuracy of classification was 53% for cases with a true N/C ratio between 0.4 and 0.8. Absolute interrater agreement was 75%. Chance corrected agreement (kappa) was 0.54. CONCLUSIONS: Visual quantitation of N/C ratio showed only a fair correlation with actual N/C ratio with correlation decreasing with increasing N/C ratio. In the critical range, 0.5-0.7 N/C ratio both interobserver correlation and correlation with true N/C ratio may be insufficiently accurate for precise category assignment as used in the Paris System. Diagn. Cytopathol. 2017;45:107-112. © 2016 Wiley Periodicals, Inc.

Quality assurance of anatomic pathology diagnoses: Comparison of alternate approaches.

OBJECTIVES: Traditionally, a 10% review has been the basis for quality assurance programs in anatomic pathology. The effectiveness of such reviews has been questioned and alternative methodologies suggested. The study investigates the error detection rates for four quality assurance protocols. METHODS: The detection rate for diagnostic errors in surgical pathology was calculated over a one year period using four different review procedures comprising: random 10% review, correlation of internal and external diagnoses following solicited external expert opinion, correlation of internal diagnoses with outside diagnoses in cases sent for review at a second institution treating the patient along with a focused review of dermatopathology cases over a 3 month period. Error rate was expressed as percentage of reviewed cases where the initial diagnosis differed from the review diagnosis. Error rates detected by each method were compared among the methods RESULTS: The 10% random review detected seventeen errors in 2147 cases (0.8%). Solicited case consultations requested by clinicians or internal pathologists detected five diagnostic errors in seventy cases (7.1%). Unsolicited reviews by outside institutions in the course of patient care detected three diagnostic errors in 190 cases (1.6%). Review of the dermatopathology material disclosed 5 diagnostic errors in 59 cases (8.5%). CONCLUSIONS: Focused reviews initiated by diagnostic concerns of a clinician or pathologist, unsolicited reviews because of treatment at another institution and sub-specialty based reviews appear to be more effective in detecting diagnostic errors than the 10% random review. Quality assurance programs should include focused reviews in addition to 10% random review to maximize error detection.

Evidence of both von Willebrand factor deposition and factor V deposition onto AL amyloid as the cause of a severe bleeding diathesis.

: Acquired coagulopathies are common; uncommonly, adsorption of coagulation factors from the circulation into the tissues by pathologic amyloid exceeds the body's ability to produce factor and results in acquired factor deficiency. When amyloidosis does cause a coagulopathy, it is most often acquired factor X deficiency, but there are rare reports of amyloidosis being associated with other acquired factor deficiencies. We investigated a case of a severe bleeding diathesis, the cause of which was combined acquired factor V deficiency and concomitant acquired von Willebrand syndrome. Studies revealed prolonged prothrombin time and activated partial thromboplastin time. Mixing patient plasma with normal plasma corrected both the prothrombin time and activated partial thromboplastin time. Assays showed decreased factor V activity of 27%; Ristocetin cofactor activity was decreased at 49%, but von Willebrand antigen was elevated at 213%. Multimer analysis was consistent with type 2 von Willebrand syndrome. Lymph node biopsy documented amyloid light chain type (AL) amyloidosis; extraction of protein from the lymph node documented AL lambda light chain amyloid. Marrow biopsy documented IgG lambda myeloma. Immunohistochemical staining of the lymph node, using investigational polyvalent antibodies, demonstrated that both von Willebrand factor and factor V were identifiable in areas of amyloid deposition, providing evidence that these coagulation factors were adsorbed to the amyloid protein, resulting in accelerated clearance from the circulation, previously reported to be the mechanism of cases of acquired factor X deficiency in the setting of amyloidosis. Although there are case reports of acquired von Willebrand syndrome because of amyloidosis and case reports of acquired factor V deficiency because of amyloidosis, this appears to be the first reported case of concomitant acquired von Willebrand syndrome and acquired factor V deficiency because of amyloidosis, and the first report of localization of both von Willebrand protein and factor V protein to AL amyloid as a cause of a severe bleeding diathesis.

Combined small-cell lung carcinoma: An institutional experience.

BACKGROUND: The purpose of this study is to determine prognostic factors and survival in patients who present with combined small-cell lung cancer (SCLC). METHODS: A retrospective review of combined SCLC histology in patients treated between1995-2010 was undertaken. Demographics, diagnostic information, disease characteristics, treatment modality, and survival were captured. Survival estimates were performed using Kaplan Meier analysis. Statistical significance was defined as P < 0.05. RESULTS: Forty-one patients were identified, and 35 records were available for analysis. Median age at diagnosis was 68 (range 50-85). The study included 20 (57%) women and 15 (43%) men; and 94% had a current or former history of smoking. Histology was SCLC/large cell carcinoma not otherwise specified in 28 (80%), and SCLC/adenocarcinoma or SCLC/squamous cell carcinoma in seven (20%). Cardiac or pulmonary comorbidities were present in 80% of patients, and 24 patients had metastatic disease at presentation. Twenty-eight patients received treatment of chemotherapy (n = 24), cranial radiotherapy (n = 5), or thoracic radiotherapy (n = 7). Staging was as follows: stage I-III (n = 11), stage IV (n = 24). Median survival was 15.4 months (range <1-53 months) and 3.4 months (range <1-21.9 months) for American Joint Committee on Cancer (AJCC) stage I-III and stage IV, respectively. Estimated overall six and 12 month survival was 82%, 55%, 37%, and 17% for stage I-III and stage IV, respectively. An improved overall survival rate was found for patients with an Eastern Cooperative Oncology Group performance status of <2, and no weight loss (P < 0.05). CONCLUSION: Akin to SCLC, advanced stage combined SCLC portends a poor prognosis. Perhaps novel chemotherapeutic drugs or targeted agents may improve outcomes for future patient populations.

Elevated peritoneal fluid TNF-α incites ovarian early growth response factor 1 expression and downstream protease mediators: a correlation with ovulatory dysfunction in endometriosis.

Endometriosis-associated infertility manifests itself via multiple, poorly understood mechanisms. Our goal was to characterize signaling pathways, between peritoneal endometriotic lesions and the ovary, leading to failed ovulation. Genome-wide microarray analysis comparing ovarian tissue from an in vivo endometriosis model in the rat (Endo) with controls (Sham) identified 22 differentially expressed genes, including transiently expressed early growth response factor 1 (Egr1). The Egr1 regulates gene requisites for ovulation. The Egr1 promoter is responsive to tumor necrosis factor-alpha (TNF-α) signaling. We hypothesized that altered expression of ovarian EGR1 is induced by elevated peritoneal fluid TNF-α which is upregulated by the presence of peritoneal endometriosis. Endo rats, compared to controls, had more peritoneal fluid TNF-α and quantitative, spatial differences in Egr1 mRNA and EGR1 protein localization in follicular compartments. Interactions between elevated peritoneal fluid TNF-α and overexpression of follicular Egr1/EGR1 expression may affect downstream protease pathways impeding ovulation in endometriosis. Preliminary studies identified similar patterns of EGR1 protein localization in human ovaries from women with endometriosis and compared to those without endometriosis.

Endometrioid adenocarcinoma metastatic to the thyroid, presenting like anaplastic thyroid cancer.

Metastasis of uterine cancer to the head and neck is extremely rare. We report what we believe to be the first documented case of endometrioid adenocarcinoma metastasizing to the thyroid gland. An 80-year-old woman was referred to the otolaryngology service with a rapidly growing neck mass. The mass appeared to originate from the thyroid gland. Her clinical presentation was consistent with anaplastic thyroid carcinoma. A tracheostomy was performed. An open biopsy established the diagnosis of moderately differentiated adenocarcinoma, consistent with a gynecologic primary. The patient had undergone a hysterectomy 5 years prior for endometrioid adenocarcinoma. The thyroid tumor histology and immunophenotype corresponded well with her prior endometrial carcinoma, indicating that the thyroid mass was a metastasis from the endometrial primary. Radiotherapy appears to offer good local disease control in this rare case of endometrioid adenocarcinoma metastatic to the thyroid.

Catamenial appendicitis.

BACKGROUND: Reproductive-aged women undergoing appendectomy for suspected appendicitis have twice the rate of negative histology as age-matched men. The reason for this discrepancy is unknown. CASES: Three patients with peritoneal endometriosis and recurrent symptoms of acute appendicitis coincident with menses underwent resection of a noninflamed appendix with long-term symptom resolution. Standard pathological evaluation failed to demonstrate evidence of appendiceal endometriosis or appendicitis. Additional evaluation demonstrated a marked increase in number of mast cells in the appendiceal muscularis compared with normal appendices. CONCLUSION: The term "catamenial appendicitis" has been coined to describe these cases, and a mechanism of pathogenesis of right lower quadrant pain and nausea in patients with histologically confirmed endometriosis is proposed.

Characterization of spontaneous mammary gland carcinomas in female baboons.

Spontaneous mammary gland carcinomas occurred in five baboons during a 13-year period at Southwest Foundation for Biomedical Research. The affected baboons ranged in age from 21 to 33 years. Menopause in the baboon occurs at approximately 26 years of age. All five animals had typical invasive ductal carcinoma. Morphologically, the tumors were characterized by neoplastic cells arranged from pseudopapillary and cribiform to more poorly differentiated solid cellular growth patterns. Additional features included lack of tubule formation (4/5), marked nuclear pleomorphism (5/5), a high mitotic rate (4/5) and tumor necrosis (4/5). Applying a grading system used for breast cancer in women, four tumors were graded as poorly differentiated carcinomas and one was graded as moderately differentiated. Co-existent ductal carcinoma in situ (DCIS) was observed in three of the mammary tumors. Metastases to the regional lymph nodes were confirmed in two animals, both with histological evidence of lymphovascular invasion in the primary tumor. Distant metastases were observed in only one animal. Immunohistochemical staining for human therapeutic markers revealed 2/5 tumors strongly positive for estrogen receptor, 1/5 strongly positive for progesterone receptor and 4/4 negative for HER2 expression. Although the incidence appears to be low, these five cases of mammary carcinoma in female baboons suggest that when present baboon mammary carcinoma is usually of ductal origin and behaves similar to a human breast carcinoma.

The pathology of extrapulmonary small cell carcinoma.

Extrapulmonary small cell carcinomas (EPSCCs) are uncommon malignant neoplasms with a reported incidence of 0.1% to 0.4% in the United States. Since their first description in 1930, they have been seen in nearly every organ system. Like their more common pulmonary counterparts, EPSCCs are thought to arise from a multipotential stem cell. However, there is recent molecular evidence that small cell elements may arise as a late-stage phenomenon in the genetic progression of more organ-typical carcinomas. The morphologic, immunohistochemical, and ultrastructural features are similar to those described in pulmonary small cell carcinomas (PSCCs). The differential diagnosis of EPSCC includes PSCC, other neuroendocrine tumors, small round blue cell tumors, metastatic melanoma, lymphoma, and poorly differentiated non-small cell carcinomas. Molecular alterations reported to occur in EPSCCs include abnormalities described in PSCC and changes found in carcinomas more typically encountered in the organ from which they arise. In this article we discuss the pathology of EPSCC with a review of theories of histogenesis, sites of occurrence, diagnostic features, differential diagnosis, molecular alterations, and clinical behavior.

1D5 and 6F11: An immunohistochemical comparison of two monoclonal antibodies for the evaluation of estrogen receptor status in primary breast carcinoma.

The optimal monoclonal antibody to examine steroid hormone receptor status of primary breast carcinoma has yet to be defined. Estrogen receptor status was evaluated in 592 cases using routinely prepared paraffin-embedded tissue samples from primary breast carcinomas with the 1D5 (DAKO, Carpinteria, CA) and 6F11 (Novocastra, Newcastle upon Tyne, England) monoclonal antibodies. The stains were compared, assessing the percentage of positive cells stained and their intensity. They also were examined for nonspecific cytoplasmic staining and fixation artifact. In addition, a cost analysis for their production was performed. Overall, 1D5 and 6F11 showed a 97.5% concordance rate. 6F11 stained a significantly higher percentage of cells (P < .0001), more intensely (P < .0001), with less nonspecific cytoplasmic staining (P < .0001). There was no significant difference in fixation artifact between the 2 clones. The cost of antibody used for preparing a 1D5-stained slide was 86% more than for preparing a 6F11-stained slide (dollars 14.27 vs dollars 7.67).